up

main.py

@@ -1,23 +1,27 @@
 from fastapi import FastAPI, File, UploadFile
-from transformers import ViTImageProcessor, ViTForImageClassification
+from transformers import AutoImageProcessor, SiglipForImageClassification
 from PIL import Image
 import torch
 import io
 
-MODEL_NAME = "ahmed-masoud/sign_language_translator"
+MODEL_NAME = "prithivMLmods/Alphabet-Sign-Language-Detection"
 
 
 try:
-    processor = ViTImageProcessor.from_pretrained(MODEL_NAME)
+    print(f"Cargando modelo '{MODEL_NAME}'...")
+    processor = AutoImageProcessor.from_pretrained(MODEL_NAME)
     
-    model = ViTForImageClassification.from_pretrained(MODEL_NAME)
+    model = SiglipForImageClassification.from_pretrained(MODEL_NAME)
     
-    print(f"Modelo '{MODEL_NAME}' cargado")
+    print(f"Modelo '{MODEL_NAME}' cargado exitosamente")
+    model_loaded = True
     
 except Exception as e:
-    print(f"Error al cargar el modelo {e}")
+    print(f"Error al cargar el modelo: {e}")
+    print("Usando modelo de ejemplo. Para uso real, necesitas un modelo específico de ASL.")
     model = None
     processor = None
+    model_loaded = False
 
 app = FastAPI(title="API de ASL con modelo de HF")
 
@@ -25,24 +29,46 @@ app = FastAPI(title="API de ASL con modelo de HF")
 @app.post("/predict/")
 async def translate_sign(file: UploadFile = File(...)):
     if not model or not processor:
-        return {"error": "Modelo no disponible."}
+        return {
+            "error": "Modelo no disponible.", 
+            "message": "El modelo específico de ASL no pudo cargarse. Verifica que el modelo existe en Hugging Face.",
+            "model_attempted": MODEL_NAME
+        }
 
-    image_bytes = await file.read()
-    image = Image.open(io.BytesIO(image_bytes))
+    try:
+        image_bytes = await file.read()
+        image = Image.open(io.BytesIO(image_bytes))
 
-    inputs = processor(images=image, return_tensors="pt")
+        inputs = processor(images=image, return_tensors="pt")
 
-    with torch.no_grad():
-        outputs = model(**inputs)
-        logits = outputs.logits
+        with torch.no_grad():
+            outputs = model(**inputs)
+            logits = outputs.logits
+            
+            probs = torch.nn.functional.softmax(logits, dim=1)
 
-    predicted_class_idx = logits.argmax(-1).item()
-    
-    predicted_label = model.config.id2label[predicted_class_idx]
+        predicted_class_idx = logits.argmax(-1).item()
+        confidence = probs[0][predicted_class_idx].item()
+        
+        predicted_label = model.config.id2label[predicted_class_idx]
 
-    return {"prediction": predicted_label}
+        return {
+            "prediction": predicted_label, 
+            "confidence": round(confidence * 100, 2) 
+        }
+    
+    except Exception as e:
+        return {"error": f"Error al procesar la imagen: {str(e)}"}
 
 
 @app.get("/")
 def read_root():
     return {"message": "API ok. Usa el endpoint /predict/ para predecir."}
+
+@app.get("/status/")
+def get_status():
+    return {
+        "model_loaded": model_loaded,
+        "model_name": MODEL_NAME,
+        "message": "Modelo cargado correctamente" if model_loaded else "Modelo no disponible"
+    }